© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30643
    Prev
    Next
    INDEX
    Explanations

    namespace .Domain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Furthermore
    -0.07
    -,
    -0.07
    éĢļè¿ĩåIJĦç§į
    -0.07
    ä¸Ģ缴éĥ½åľ¨
    -0.07
    æ´»èºį
    -0.06
    æīĢ使çĶ¨çļĦ
    -0.06
    bar
    -0.06
    Âł
    -0.06
    æīĢæıIJä¾ĽçļĦ
    -0.06
    /$
    -0.06
    POSITIVE LOGITS
    ream
    0.09
    "":
    0.08
    spb
    0.08
    utilise
    0.08
    ":
    0.08
    *:
    0.08
    __:
    0.08
    ":[{"
    0.08
     {}:
    0.08
    zia
    0.07
    Activations Density 0.002%

    No Known Activations